Presentation 2014-11-22
A simulation study of a neural network model for detecting planar surface by motion stereo vision
Hisanao AKIMA, Susumu KAWAKAMI, Koji NAKAJIMA, Masao SAKURABA, Shigeo SATO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The spatial perception, in which objects motion and positional relation are recognized, is necessary to realize such as a walking robot and an autonomous car. Although conventional methods require enormous computational resources (CPU speed, memory capacity) to process the spatial perception in real time, animals can do with less resources based on visual information. We focus on motion stereo vision, which is adopted even by insects and birds, and aim to construct a low-power spatial perception system by implementing the neural network model proposed by Kawakami et.al. as a LSI. In this study, we reduce memory capacity and operation amount so as to fit in a LSI and show cell responses of the model using computer simulation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Motion Stereo Vision / Middle Temporal Area / Optical Flow / Local-motion Detection / LSI
Paper # NC2014-43
Date of Issue

Conference Information
Committee NC
Conference Date 2014/11/14(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A simulation study of a neural network model for detecting planar surface by motion stereo vision
Sub Title (in English)
Keyword(1) Motion Stereo Vision
Keyword(2) Middle Temporal Area
Keyword(3) Optical Flow
Keyword(4) Local-motion Detection
Keyword(5) LSI
1st Author's Name Hisanao AKIMA
1st Author's Affiliation Research Institute of Electrical Communication Tohoku University()
2nd Author's Name Susumu KAWAKAMI
2nd Author's Affiliation / Research Institute of Electrical Communication Tohoku University
3rd Author's Name Koji NAKAJIMA
3rd Author's Affiliation Research Institute of Electrical Communication Tohoku University
4th Author's Name Masao SAKURABA
4th Author's Affiliation Research Institute of Electrical Communication Tohoku University
5th Author's Name Shigeo SATO
5th Author's Affiliation
Date 2014-11-22
Paper # NC2014-43
Volume (vol) vol.114
Number (no) 326
Page pp.pp.-
#Pages 4
Date of Issue